Archive for workshop
off to Sabhal Mòr Ostaig, Eilean Sgitheanach
Posted in Books, Mountains, pictures, Running, Statistics, Travel, University life with tags approximate Bayesian inference, approximately Bayes, Eilean Sgitheanach, Frances Walker, ICMS, Inner Hebrides, Isle of Skye Brewery, Sabhal Mor Ostaig, Scotland, Scottish Gaelic, workshop on May 17, 2026 by xi'an
the vexing Hausdorff measure
Posted in Books, Statistics, University life with tags Claude, Computational methods for probability distributions on manifolds, Hausdorff metric, IHP, Institut Henri Poincaré, LLMs, manifold exploration, MCMC, Paris, workshop on May 13, 2026 by xi'anAttending the workshop “Computational methods for probability distributions on manifolds” (IHP, Paris, May 11-13, 2026) made me re-ponder the challenge of simulating a distribution conditional on the random variable X~p(x) being constrained to the manifold M defined by q(x)=0. Fortunately, Claude helped a lot in downgrading the importance of the Hausdorff measure σ! The density writes p(x)/||∇q(x)||, with respect to the Hausdorff measure on M. Which accounts for the curvature of the manifold M. When resorting to an MCMC algorithm to simulate this density, there are two options: (a) simulate from a proposal on the manifold M whose density wrt the Hausdorff measure σ is known or (b) resort to a reparameterisation map φ of the manifold M whose input on an Euclidean space has density
wrt the Lebesgue measure.
computational methods for probability distributions on manifolds (11-13 May, IHP, Paris)
Posted in Books, pictures, Statistics, Travel, University life with tags bootstrap, experimental design, generative model, Gromov-Wasserstein, IHP, Institut Henri Poincaré, inverse problems, kernel Stein discrepancy descent, manifold, manifold exploration, MCMC, mixture models, Paris, workshop on May 12, 2026 by xi'an
This week, we are running a small workshop on Computational methods for probability distributions on manifolds, whose size was dictated by the corresponding surface of the Institut Henri room allotted to us by the IHP administration. Very exciting theme and very exciting program, which more than make up for the unseasonal weather in Paris.
May 11
Guillaume Pouliot – MCMC on Manifolds in Economics
Alessandro Barp – Kernel and Stein discrepancies between distributions, à la Schwartz
Robin Ryder – Coupling MCMC on manifolds
Chang-Han Rhee – Experimental Design on Manifolds
May 12
Gilles Vilmart – High-order sampling of the invariant distribution of ergodic stochastic dynamics: preconditioning and postprocessing
Paul Breiding – Sampling from or near nonlinear algebraic varieties
Nick Whiteley – Statistical exploration of the Manifold Hypothesis
Judith Rousseau – Denoising diffusion Models under the Manifold Hypothesis : A dimension free convergence rate
Manon Michel – Convergence of non-reversible Markov processes via lifting and Flow Poincaré inequality
Tobias Grafke – Sampling Conditioned Diffusions via Pathspace Projected Monte Carlo
Miranda Holmes-Cerfon – Simulating sticky Brownian motion
Agnès Desolneux – Distances “à la Gromov-Wasserstein” for Gaussian Mixture Models
May 13
Giovanni Samaey – Multilevel interacting particle methods for sampling Bayesian inverse problems
Marylou Gabrié – Revisiting enhanced sampling driven by collective variables using generative models
Chris Walker – A Bayesian Perspective on the Maximum Score Problem
Lulu Kang – Active Learning for Manifold Gaussian Process Regression
room with [what] a view [jatp]
Posted in pictures, Travel, University life with tags architecture, Canal Grande, conference room, historical building, Italia, jatp, Università Ca' Foscari Venezia, Venezia, view, visiting position, workshop on May 7, 2026 by xi'an
SEINE AI
Posted in pictures, Statistics, University life with tags #ERCSyG, adversarial learning, agent-based models, bandits, Bayesian learning, Bradley–Terry–Luce model, ChatGPT, hallucinations, Information and Communication Technology, INRIA, John Nash, Jouy-en-Josas, LLM, München, multi-agent decision theory, Nash equilibrium, Paris, Queen Mary University of London, reinforcement learning, Seine, slideshare, workshop, ye Norse farce on March 23, 2026 by xi'an
Ten days ago I took part in the SEINE AI 2026 workshop in Jouy-en-Josas, near Paris (homestead of HEC), organised by the Huawei Paris Research Center.. In which I was invited to speak, even though I felt sort of an outlier given the deeply machine-learning, entreprenarial orientation of the meeting, with its theme being Building the Agentic Future of ICT, given that I chose to present our most recent Bayesian adversarial privacy paper. Hence, I stood within a game-theoretic, Bayesian, formal landscape, presumably loosing most of the audience and keeping them away from their lunch!
Other speakers included Simon Lucas from Queen Mary London on Simulation-based AI, which I had trouble distinguishing from building a statistical model by goodness of fit (and using bandits used for update), while focussing on competing on some computer game challenges. And Volker Tresp from LMU München on a tensor brain model that he opposes to a Bayesian brain (with a related paper entitled Bayes or Heisenberg: Who(se) rules? which we discussed in general terms over lunch, namely Bayesian learning vs. quantum updating. And Michal Valko from INRIA Paris (and other companies), who went full blast against the Bradley-Terry model!, with a title of Nash and Nemirovski walk into a bar! With a half-time technique approximating Nash equilibria that reminded me of leapfrog. Much entertaining talk that further provided a game-theoretic transition to mine’s.
As an aside, I played yesterday with ChatGPT composing my talk slides out of our arXiv document and it proved a disaster, with hallucinations of results and concepts not in the paper and a complete mess of handling graphs, first creating generic, fake, unrelated pictures, then inserting actual graphs haphazardly throughout the slides. The sorry result I obviously did not use as the workshop did not seem the ideal place for this sort of prank! The actual version only recycles a few of its summarising slides. (With ye Norse farce proper colour choice!)
